diff options
Diffstat (limited to 'net/ipv4')
31 files changed, 834 insertions, 476 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e31108e5ef79..ce4aa827be05 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -195,7 +195,7 @@ int inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; unsigned char old_state; - int err; + int err, tcp_fastopen; lock_sock(sk); @@ -217,11 +217,12 @@ int inet_listen(struct socket *sock, int backlog) * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ - if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && - (sysctl_tcp_fastopen & TFO_SERVER_ENABLE) && + tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && + (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { fastopen_queue_tune(sk, backlog); - tcp_fastopen_init_key_once(true); + tcp_fastopen_init_key_once(sock_net(sk)); } err = inet_csk_listen_start(sk, backlog); @@ -826,6 +827,7 @@ int inet_shutdown(struct socket *sock, int how) err = -ENOTCONN; /* Hack to wake up other listeners, who can poll for POLLHUP, even on eg. unconnected UDP sockets -- RR */ + /* fall through */ default: sk->sk_shutdown |= how; if (sk->sk_prot->shutdown) @@ -839,7 +841,7 @@ int inet_shutdown(struct socket *sock, int how) case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; - /* Fall through */ + /* fall through */ case TCP_SYN_SENT: err = sk->sk_prot->disconnect(sk, O_NONBLOCK); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 7c45b8896709..a8d7c5a9fb05 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1180,6 +1180,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCSARP: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; + /* fall through */ case SIOCGARP: err = copy_from_user(&r, arg, sizeof(struct arpreq)); if (err) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 7ce22a2c07ce..e1e2ec0525e6 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1522,6 +1522,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (inetdev_valid_mtu(dev->mtu)) break; /* disable IP when MTU is not enough */ + /* fall through */ case NETDEV_UNREGISTER: inetdev_destroy(in_dev); break; @@ -1757,7 +1758,7 @@ static int inet_validate_link_af(const struct net_device *dev, struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; - if (dev && !__in_dev_get_rtnl(dev)) + if (dev && !__in_dev_get_rcu(dev)) return -EAFNOSUPPORT; err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy, NULL); @@ -1781,7 +1782,7 @@ static int inet_validate_link_af(const struct net_device *dev, static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) { - struct in_device *in_dev = __in_dev_get_rtnl(dev); + struct in_device *in_dev = __in_dev_get_rcu(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; int rem; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 57a5d48acee8..467b3c15395f 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -601,17 +601,9 @@ static void fib_rebalance(struct fib_info *fi) atomic_set(&nexthop_nh->nh_upper_bound, upper_bound); } endfor_nexthops(fi); } - -static inline void fib_add_weight(struct fib_info *fi, - const struct fib_nh *nh) -{ - fi->fib_weight += nh->nh_weight; -} - #else /* CONFIG_IP_ROUTE_MULTIPATH */ #define fib_rebalance(fi) do { } while (0) -#define fib_add_weight(fi, nh) do { } while (0) #endif /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -774,8 +766,8 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) * | * |-> {local prefix} (terminal node) */ -static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, - struct fib_nh *nh, struct netlink_ext_ack *extack) +static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh, + struct netlink_ext_ack *extack) { int err = 0; struct net *net; @@ -1258,7 +1250,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, int linkdown = 0; change_nexthops(fi) { - err = fib_check_nh(cfg, fi, nexthop_nh, extack); + err = fib_check_nh(cfg, nexthop_nh, extack); if (err != 0) goto failure; if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN) @@ -1275,7 +1267,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg, change_nexthops(fi) { fib_info_update_nh_saddr(net, nexthop_nh); - fib_add_weight(fi, nexthop_nh); } endfor_nexthops(fi) fib_rebalance(fi); diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 416bb304a281..1859c473b21a 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -86,7 +86,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, greh = (struct gre_base_hdr *)skb_transport_header(skb); pcsum = (__sum16 *)(greh + 1); - if (gso_partial) { + if (gso_partial && skb_is_gso(skb)) { unsigned int partial_adj; /* Adjust checksum to account for the fact that diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 681e33998e03..3c1570d3e22f 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -782,7 +782,7 @@ static bool icmp_tag_validation(int proto) } /* - * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and + * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEEDED, ICMP_QUENCH, and * ICMP_PARAMETERPROB. */ @@ -810,7 +810,8 @@ static bool icmp_unreach(struct sk_buff *skb) if (iph->ihl < 5) /* Mangled header, drop. */ goto out_err; - if (icmph->type == ICMP_DEST_UNREACH) { + switch (icmph->type) { + case ICMP_DEST_UNREACH: switch (icmph->code & 15) { case ICMP_NET_UNREACH: case ICMP_HOST_UNREACH: @@ -846,8 +847,16 @@ static bool icmp_unreach(struct sk_buff *skb) } if (icmph->code > NR_ICMP_UNREACH) goto out; - } else if (icmph->type == ICMP_PARAMETERPROB) + break; + case ICMP_PARAMETERPROB: info = ntohl(icmph->un.gateway) >> 24; + break; + case ICMP_TIME_EXCEEDED: + __ICMP_INC_STATS(net, ICMP_MIB_INTIMEEXCDS); + if (icmph->code == ICMP_EXC_FRAGTIME) + goto out; + break; + } /* * Throw it at our lower layers diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 8a91ebbf0c01..5c965ecc96a0 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -494,17 +494,15 @@ EXPORT_SYMBOL(inet_csk_accept); * to optimize. */ void inet_csk_init_xmit_timers(struct sock *sk, - void (*retransmit_handler)(unsigned long), - void (*delack_handler)(unsigned long), - void (*keepalive_handler)(unsigned long)) + void (*retransmit_handler)(struct timer_list *t), + void (*delack_handler)(struct timer_list *t), + void (*keepalive_handler)(struct timer_list *t)) { struct inet_connection_sock *icsk = inet_csk(sk); - setup_timer(&icsk->icsk_retransmit_timer, retransmit_handler, - (unsigned long)sk); - setup_timer(&icsk->icsk_delack_timer, delack_handler, - (unsigned long)sk); - setup_timer(&sk->sk_timer, keepalive_handler, (unsigned long)sk); + timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0); + timer_setup(&icsk->icsk_delack_timer, delack_handler, 0); + timer_setup(&sk->sk_timer, keepalive_handler, 0); icsk->icsk_pending = icsk->icsk_ack.pending = 0; } EXPORT_SYMBOL(inet_csk_init_xmit_timers); @@ -676,9 +674,9 @@ void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); -static void reqsk_timer_handler(unsigned long data) +static void reqsk_timer_handler(struct timer_list *t) { - struct request_sock *req = (struct request_sock *)data; + struct request_sock *req = from_timer(req, t, rsk_timer); struct sock *sk_listener = req->rsk_listener; struct net *net = sock_net(sk_listener); struct inet_connection_sock *icsk = inet_csk(sk_listener); @@ -749,8 +747,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, req->num_timeout = 0; req->sk = NULL; - setup_pinned_timer(&req->rsk_timer, reqsk_timer_handler, - (unsigned long)req); + timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); inet_ehash_insert(req_to_sk(req), NULL); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index af74d0433453..7f3ef5c287a1 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -147,7 +147,7 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) spin_unlock(&hb->chain_lock); hlist_for_each_entry_safe(fq, n, &expired, list_evictor) - f->frag_expire((unsigned long) fq); + f->frag_expire(&fq->timer); return evicted; } @@ -366,7 +366,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, f->constructor(q, arg); add_frag_mem_limit(nf, f->qsize); - setup_timer(&q->timer, f->frag_expire, (unsigned long)q); + timer_setup(&q->timer, f->frag_expire, 0); spin_lock_init(&q->lock); refcount_set(&q->refcnt, 1); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 5b039159e67a..a4bab81f1462 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -142,9 +142,9 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, } EXPORT_SYMBOL_GPL(__inet_twsk_hashdance); -static void tw_timer_handler(unsigned long data) +static void tw_timer_handler(struct timer_list *t) { - struct inet_timewait_sock *tw = (struct inet_timewait_sock *)data; + struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer); if (tw->tw_kill) __NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED); @@ -188,8 +188,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, tw->tw_prot = sk->sk_prot_creator; atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie)); twsk_net_set(tw, sock_net(sk)); - setup_pinned_timer(&tw->tw_timer, tw_timer_handler, - (unsigned long)tw); + timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED); /* * Because we use RCU lookups, we should not set tw_refcnt * to a non null value before everything is setup for this diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e7eb590c86ce..914d56928578 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -128,9 +128,9 @@ static struct inet_peer *lookup(const struct inetpeer_addr *daddr, break; } if (cmp == -1) - pp = &(*pp)->rb_left; + pp = &next->rb_left; else - pp = &(*pp)->rb_right; + pp = &next->rb_right; } *parent_p = parent; *pp_p = pp; @@ -284,14 +284,17 @@ EXPORT_SYMBOL(inet_peer_xrlim_allow); void inetpeer_invalidate_tree(struct inet_peer_base *base) { - struct inet_peer *p, *n; + struct rb_node *p = rb_first(&base->rb_root); - rbtree_postorder_for_each_entry_safe(p, n, &base->rb_root, rb_node) { - inet_putpeer(p); + while (p) { + struct inet_peer *peer = rb_entry(p, struct inet_peer, rb_node); + + p = rb_next(p); + rb_erase(&peer->rb_node, &base->rb_root); + inet_putpeer(peer); cond_resched(); } - base->rb_root = RB_ROOT; base->total = 0; } EXPORT_SYMBOL(inetpeer_invalidate_tree); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 46408c220d9d..9215654a401f 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -190,12 +190,13 @@ static bool frag_expire_skip_icmp(u32 user) /* * Oops, a fragment queue timed out. Kill it and send an ICMP reply. */ -static void ip_expire(unsigned long arg) +static void ip_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct ipq *qp; struct net *net; - qp = container_of((struct inet_frag_queue *) arg, struct ipq, q); + qp = container_of(frag, struct ipq, q); net = container_of(qp->q.net, struct net, ipv4.frags); rcu_read_lock(); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 9cee986ac6b8..c105a315b1a3 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -259,7 +259,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct ip_tunnel *tunnel; struct erspanhdr *ershdr; const struct iphdr *iph; - __be32 session_id; __be32 index; int len; @@ -275,8 +274,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, /* The original GRE header does not have key field, * Use ERSPAN 10-bit session ID as key. */ - session_id = cpu_to_be32(ntohs(ershdr->session_id)); - tpi->key = session_id; + tpi->key = cpu_to_be32(ntohs(ershdr->session_id) & ID_MASK); index = ershdr->md.index; tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, @@ -581,8 +579,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, if (gre_handle_offloads(skb, false)) goto err_free_rt; - if (skb->len > dev->mtu) { - pskb_trim(skb, dev->mtu); + if (skb->len > dev->mtu + dev->hard_header_len) { + pskb_trim(skb, dev->mtu + dev->hard_header_len); truncate = true; } @@ -733,8 +731,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; - if (skb->len > dev->mtu) { - pskb_trim(skb, dev->mtu); + if (skb->len > dev->mtu + dev->hard_header_len) { + pskb_trim(skb, dev->mtu + dev->hard_header_len); truncate = true; } @@ -1222,6 +1220,7 @@ static int gre_tap_init(struct net_device *dev) { __gre_tunnel_init(dev); dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netif_keep_dst(dev); return ip_tunnel_init(dev); } @@ -1245,13 +1244,16 @@ static int erspan_tunnel_init(struct net_device *dev) tunnel->tun_hlen = 8; tunnel->parms.iph.protocol = IPPROTO_GRE; - t_hlen = tunnel->hlen + sizeof(struct iphdr) + sizeof(struct erspanhdr); + tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + + sizeof(struct erspanhdr); + t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; dev->mtu = ETH_DATA_LEN - t_hlen - 4; dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netif_keep_dst(dev); return ip_tunnel_init(dev); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index fa2dc8f692c6..57fc13c6ab2b 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -311,9 +311,10 @@ drop: static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); - struct rtable *rt; + int (*edemux)(struct sk_buff *skb); struct net_device *dev = skb->dev; - void (*edemux)(struct sk_buff *skb); + struct rtable *rt; + int err; /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -331,7 +332,9 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) ipprot = rcu_dereference(inet_protos[protocol]); if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) { - edemux(skb); + err = edemux(skb); + if (unlikely(err)) + goto drop_error; /* must reload iph, skb->head might have changed */ iph = ip_hdr(skb); } @@ -342,13 +345,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) * how the packet travels inside Linux networking. */ if (!skb_valid_dst(skb)) { - int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, - iph->tos, dev); - if (unlikely(err)) { - if (err == -EXDEV) - __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); - goto drop; - } + err = ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, dev); + if (unlikely(err)) + goto drop_error; } #ifdef CONFIG_IP_ROUTE_CLASSID @@ -399,6 +399,11 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) drop: kfree_skb(skb); return NET_RX_DROP; + +drop_error: + if (err == -EXDEV) + __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); + goto drop; } /* diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 02d70ca99db1..58465c0a8682 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -168,6 +168,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, struct ip_tunnel_parm *parms = &tunnel->parms; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ + int pkt_len = skb->len; int err; int mtu; @@ -229,7 +230,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) - err = skb->len; + err = pkt_len; iptunnel_xmit_stats(dev, err); return NETDEV_TX_OK; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c9b3e6e069ae..40a43ad294cb 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -67,6 +67,7 @@ #include <net/fib_rules.h> #include <linux/netconf.h> #include <net/nexthop.h> +#include <net/switchdev.h> struct ipmr_rule { struct fib_rule common; @@ -264,6 +265,22 @@ static void __net_exit ipmr_rules_exit(struct net *net) fib_rules_unregister(net->ipv4.mr_rules_ops); rtnl_unlock(); } + +static int ipmr_rules_dump(struct net *net, struct notifier_block *nb) +{ + return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR); +} + +static unsigned int ipmr_rules_seq_read(struct net *net) +{ + return fib_rules_seq_read(net, RTNL_FAMILY_IPMR); +} + +bool ipmr_rule_default(const struct fib_rule *rule) +{ + return fib_rule_matchall(rule) && rule->table == RT_TABLE_DEFAULT; +} +EXPORT_SYMBOL(ipmr_rule_default); #else #define ipmr_for_each_table(mrt, net) \ for (mrt = net->ipv4.mrt; mrt; mrt = NULL) @@ -298,6 +315,22 @@ static void __net_exit ipmr_rules_exit(struct net *net) net->ipv4.mrt = NULL; rtnl_unlock(); } + +static int ipmr_rules_dump(struct net *net, struct notifier_block *nb) +{ + return 0; +} + +static unsigned int ipmr_rules_seq_read(struct net *net) +{ + return 0; +} + +bool ipmr_rule_default(const struct fib_rule *rule) +{ + return true; +} +EXPORT_SYMBOL(ipmr_rule_default); #endif static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg, @@ -587,6 +620,82 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) } #endif +static int call_ipmr_vif_entry_notifier(struct notifier_block *nb, + struct net *net, + enum fib_event_type event_type, + struct vif_device *vif, + vifi_t vif_index, u32 tb_id) +{ + struct vif_entry_notifier_info info = { + .info = { + .family = RTNL_FAMILY_IPMR, + .net = net, + }, + .dev = vif->dev, + .vif_index = vif_index, + .vif_flags = vif->flags, + .tb_id = tb_id, + }; + + return call_fib_notifier(nb, net, event_type, &info.info); +} + +static int call_ipmr_vif_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct vif_device *vif, + vifi_t vif_index, u32 tb_id) +{ + struct vif_entry_notifier_info info = { + .info = { + .family = RTNL_FAMILY_IPMR, + .net = net, + }, + .dev = vif->dev, + .vif_index = vif_index, + .vif_flags = vif->flags, + .tb_id = tb_id, + }; + + ASSERT_RTNL(); + net->ipv4.ipmr_seq++; + return call_fib_notifiers(net, event_type, &info.info); +} + +static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb, + struct net *net, + enum fib_event_type event_type, + struct mfc_cache *mfc, u32 tb_id) +{ + struct mfc_entry_notifier_info info = { + .info = { + .family = RTNL_FAMILY_IPMR, + .net = net, + }, + .mfc = mfc, + .tb_id = tb_id + }; + + return call_fib_notifier(nb, net, event_type, &info.info); +} + +static int call_ipmr_mfc_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct mfc_cache *mfc, u32 tb_id) +{ + struct mfc_entry_notifier_info info = { + .info = { + .family = RTNL_FAMILY_IPMR, + .net = net, + }, + .mfc = mfc, + .tb_id = tb_id + }; + + ASSERT_RTNL(); + net->ipv4.ipmr_seq++; + return call_fib_notifiers(net, event_type, &info.info); +} + /** * vif_delete - Delete a VIF entry * @notify: Set to 1, if the caller is a notifier_call @@ -594,6 +703,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) static int vif_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { + struct net *net = read_pnet(&mrt->net); struct vif_device *v; struct net_device *dev; struct in_device *in_dev; @@ -603,6 +713,10 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, v = &mrt->vif_table[vifi]; + if (VIF_EXISTS(mrt, vifi)) + call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_DEL, v, vifi, + mrt->id); + write_lock_bh(&mrt_lock); dev = v->dev; v->dev = NULL; @@ -652,10 +766,11 @@ static void ipmr_cache_free_rcu(struct rcu_head *head) kmem_cache_free(mrt_cachep, c); } -static inline void ipmr_cache_free(struct mfc_cache *c) +void ipmr_cache_free(struct mfc_cache *c) { call_rcu(&c->rcu, ipmr_cache_free_rcu); } +EXPORT_SYMBOL(ipmr_cache_free); /* Destroy an unresolved cache entry, killing queued skbs * and reporting error to netlink readers. @@ -754,6 +869,9 @@ static int vif_add(struct net *net, struct mr_table *mrt, struct vifctl *vifc, int mrtsock) { int vifi = vifc->vifc_vifi; + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, + }; struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct in_device *in_dev; @@ -828,6 +946,13 @@ static int vif_add(struct net *net, struct mr_table *mrt, /* Fill in the VIF structures */ + attr.orig_dev = dev; + if (!switchdev_port_attr_get(dev, &attr)) { + memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len); + v->dev_parent_id.id_len = attr.u.ppid.id_len; + } else { + v->dev_parent_id.id_len = 0; + } v->rate_limit = vifc->vifc_rate_limit; v->local = vifc->vifc_lcl_addr.s_addr; v->remote = vifc->vifc_rmt_addr.s_addr; @@ -851,6 +976,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, if (vifi+1 > mrt->maxvif) mrt->maxvif = vifi+1; write_unlock_bh(&mrt_lock); + call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, vifi, mrt->id); return 0; } @@ -949,6 +1075,7 @@ static struct mfc_cache *ipmr_cache_alloc(void) if (c) { c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->mfc_un.res.minvif = MAXVIFS; + refcount_set(&c->mfc_un.res.refcount, 1); } return c; } @@ -1150,6 +1277,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) { + struct net *net = read_pnet(&mrt->net); struct mfc_cache *c; /* The entries are added/deleted only under RTNL */ @@ -1161,8 +1289,9 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) return -ENOENT; rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id); mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_cache_free(c); + ipmr_cache_put(c); return 0; } @@ -1189,6 +1318,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c, + mrt->id); mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1238,6 +1369,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, ipmr_cache_resolve(net, mrt, uc, c); ipmr_cache_free(uc); } + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id); mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1245,6 +1377,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, /* Close the multicast socket, and clear the vif tables etc */ static void mroute_clean_tables(struct mr_table *mrt, bool all) { + struct net *net = read_pnet(&mrt->net); struct mfc_cache *c, *tmp; LIST_HEAD(list); int i; @@ -1263,8 +1396,10 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, + mrt->id); mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_cache_free(c); + ipmr_cache_put(c); } if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { @@ -1393,6 +1528,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, case MRT_ADD_MFC: case MRT_DEL_MFC: parent = -1; + /* fall through */ case MRT_ADD_MFC_PROXY: case MRT_DEL_MFC_PROXY: if (optlen != sizeof(mfc)) { @@ -1724,10 +1860,33 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk, return dst_output(net, sk, skb); } +#ifdef CONFIG_NET_SWITCHDEV +static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, + int in_vifi, int out_vifi) +{ + struct vif_device *out_vif = &mrt->vif_table[out_vifi]; + struct vif_device *in_vif = &mrt->vif_table[in_vifi]; + + if (!skb->offload_mr_fwd_mark) + return false; + if (!out_vif->dev_parent_id.id_len || !in_vif->dev_parent_id.id_len) + return false; + return netdev_phys_item_id_same(&out_vif->dev_parent_id, + &in_vif->dev_parent_id); +} +#else +static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, + int in_vifi, int out_vifi) +{ + return false; +} +#endif + /* Processing handlers for ipmr_forward */ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, - struct sk_buff *skb, struct mfc_cache *c, int vifi) + int in_vifi, struct sk_buff *skb, + struct mfc_cache *c, int vifi) { const struct iphdr *iph = ip_hdr(skb); struct vif_device *vif = &mrt->vif_table[vifi]; @@ -1748,6 +1907,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, goto out_free; } + if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi)) + goto out_free; + if (vif->flags & VIFF_TUNNEL) { rt = ip_route_output_ports(net, &fl4, NULL, vif->remote, vif->local, @@ -1925,8 +2087,8 @@ forward: struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(net, mrt, skb2, cache, - psend); + ipmr_queue_xmit(net, mrt, true_vifi, + skb2, cache, psend); } psend = ct; } @@ -1937,9 +2099,10 @@ last_forward: struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(net, mrt, skb2, cache, psend); + ipmr_queue_xmit(net, mrt, true_vifi, skb2, + cache, psend); } else { - ipmr_queue_xmit(net, mrt, skb, cache, psend); + ipmr_queue_xmit(net, mrt, true_vifi, skb, cache, psend); return; } } @@ -2156,6 +2319,9 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0) return -EMSGSIZE; + if (c->mfc_flags & MFC_OFFLOAD) + rtm->rtm_flags |= RTNH_F_OFFLOAD; + if (!(mp_attr = nla_nest_start(skb, RTA_MULTIPATH))) return -EMSGSIZE; @@ -3048,14 +3214,87 @@ static const struct net_protocol pim_protocol = { }; #endif +static unsigned int ipmr_seq_read(struct net *net) +{ + ASSERT_RTNL(); + + return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net); +} + +static int ipmr_dump(struct net *net, struct notifier_block *nb) +{ + struct mr_table *mrt; + int err; + + err = ipmr_rules_dump(net, nb); + if (err) + return err; + + ipmr_for_each_table(mrt, net) { + struct vif_device *v = &mrt->vif_table[0]; + struct mfc_cache *mfc; + int vifi; + + /* Notifiy on table VIF entries */ + read_lock(&mrt_lock); + for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) { + if (!v->dev) + continue; + + call_ipmr_vif_entry_notifier(nb, net, FIB_EVENT_VIF_ADD, + v, vifi, mrt->id); + } + read_unlock(&mrt_lock); + + /* Notify on table MFC entries */ + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) + call_ipmr_mfc_entry_notifier(nb, net, + FIB_EVENT_ENTRY_ADD, mfc, + mrt->id); + } + + return 0; +} + +static const struct fib_notifier_ops ipmr_notifier_ops_template = { + .family = RTNL_FAMILY_IPMR, + .fib_seq_read = ipmr_seq_read, + .fib_dump = ipmr_dump, + .owner = THIS_MODULE, +}; + +static int __net_init ipmr_notifier_init(struct net *net) +{ + struct fib_notifier_ops *ops; + + net->ipv4.ipmr_seq = 0; + + ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + net->ipv4.ipmr_notifier_ops = ops; + + return 0; +} + +static void __net_exit ipmr_notifier_exit(struct net *net) +{ + fib_notifier_ops_unregister(net->ipv4.ipmr_notifier_ops); + net->ipv4.ipmr_notifier_ops = NULL; +} + /* Setup for IP multicast routing */ static int __net_init ipmr_net_init(struct net *net) { int err; + err = ipmr_notifier_init(net); + if (err) + goto ipmr_notifier_fail; + err = ipmr_rules_init(net); if (err < 0) - goto fail; + goto ipmr_rules_fail; #ifdef CONFIG_PROC_FS err = -ENOMEM; @@ -3072,7 +3311,9 @@ proc_cache_fail: proc_vif_fail: ipmr_rules_exit(net); #endif -fail: +ipmr_rules_fail: + ipmr_notifier_exit(net); +ipmr_notifier_fail: return err; } @@ -3082,6 +3323,7 @@ static void __net_exit ipmr_net_exit(struct net *net) remove_proc_entry("ip_mr_cache", net->proc_net); remove_proc_entry("ip_mr_vif", net->proc_net); #endif + ipmr_notifier_exit(net); ipmr_rules_exit(net); } diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 811689e523c3..f75fc6b53115 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -330,7 +330,8 @@ static unsigned int ipv4_synproxy_hook(void *priv, if (synproxy == NULL) return NF_ACCEPT; - if (nf_is_loopback_packet(skb)) + if (nf_is_loopback_packet(skb) || + ip_hdr(skb)->protocol != IPPROTO_TCP) return NF_ACCEPT; thoff = ip_hdrlen(skb); diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index a0f37b208268..0443ca4120b0 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -276,7 +276,8 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, else return NF_ACCEPT; } - /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + /* Only ICMPs can be IP_CT_IS_REPLY: */ + /* fall through */ case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 94d4cd2d5ea4..4306db827374 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1520,43 +1520,56 @@ struct rtable *rt_dst_alloc(struct net_device *dev, EXPORT_SYMBOL(rt_dst_alloc); /* called in rcu_read_lock() section */ -static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev, int our) +int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, + struct in_device *in_dev, u32 *itag) { - struct rtable *rth; - struct in_device *in_dev = __in_dev_get_rcu(dev); - unsigned int flags = RTCF_MULTICAST; - u32 itag = 0; int err; /* Primary sanity checks. */ - if (!in_dev) return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || skb->protocol != htons(ETH_P_IP)) - goto e_inval; + return -EINVAL; if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev)) - goto e_inval; + return -EINVAL; if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr)) - goto e_inval; + return -EINVAL; } else { err = fib_validate_source(skb, saddr, 0, tos, 0, dev, - in_dev, &itag); + in_dev, itag); if (err < 0) - goto e_err; + return err; } + return 0; +} + +/* called in rcu_read_lock() section */ +static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, int our) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + unsigned int flags = RTCF_MULTICAST; + struct rtable *rth; + u32 itag = 0; + int err; + + err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag); + if (err) + return err; + if (our) flags |= RTCF_LOCAL; rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false); if (!rth) - goto e_nobufs; + return -ENOBUFS; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; @@ -1572,13 +1585,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, skb_dst_set(skb, &rth->dst); return 0; - -e_nobufs: - return -ENOBUFS; -e_inval: - return -EINVAL; -e_err: - return err; } @@ -2507,7 +2513,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or struct rtable *ort = (struct rtable *) dst_orig; struct rtable *rt; - rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0); + rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0); if (rt) { struct dst_entry *new = &rt->dst; @@ -3032,7 +3038,6 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; int __init ip_rt_init(void) { - int rc = 0; int cpu; ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL); @@ -3089,7 +3094,7 @@ int __init ip_rt_init(void) #endif register_pernet_subsys(&rt_genid_ops); register_pernet_subsys(&ipv4_inetpeer_ops); - return rc; + return 0; } #ifdef CONFIG_SYSCTL diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0d3c038d7b04..cac8dd309f39 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -251,10 +251,12 @@ static int proc_allowed_congestion_control(struct ctl_table *ctl, return ret; } -static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, +static int proc_tcp_fastopen_key(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct net *net = container_of(table->data, struct net, + ipv4.sysctl_tcp_fastopen); struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; struct tcp_fastopen_context *ctxt; int ret; @@ -265,7 +267,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, return -ENOMEM; rcu_read_lock(); - ctxt = rcu_dereference(tcp_fastopen_ctx); + ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctxt) memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); else @@ -282,12 +284,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, ret = -EINVAL; goto bad_key; } - /* Generate a dummy secret but don't publish it. This - * is needed so we don't regenerate a new key on the - * first invocation of tcp_fastopen_cookie_gen - */ - tcp_fastopen_init_key_once(false); - tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH); + tcp_fastopen_reset_cipher(net, user_key, TCP_FASTOPEN_KEY_LENGTH); } bad_key: @@ -358,11 +355,13 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct net *net = container_of(table->data, struct net, + ipv4.sysctl_tcp_fastopen_blackhole_timeout); int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) - tcp_fastopen_active_timeout_reset(); + atomic_set(&net->ipv4.tfo_active_disable_times, 0); return ret; } @@ -401,27 +400,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .procname = "tcp_fastopen", - .data = &sysctl_tcp_fastopen, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "tcp_fastopen_key", - .mode = 0600, - .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10), - .proc_handler = proc_tcp_fastopen_key, - }, - { - .procname = "tcp_fastopen_blackhole_timeout_sec", - .data = &sysctl_tcp_fastopen_blackhole_timeout, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_tfo_blackhole_detect_timeout, - .extra1 = &zero, - }, - { .procname = "tcp_abort_on_overflow", .data = &sysctl_tcp_abort_on_overflow, .maxlen = sizeof(int), @@ -1085,6 +1063,28 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_fastopen", + .data = &init_net.ipv4.sysctl_tcp_fastopen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "tcp_fastopen_key", + .mode = 0600, + .data = &init_net.ipv4.sysctl_tcp_fastopen, + .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10), + .proc_handler = proc_tcp_fastopen_key, + }, + { + .procname = "tcp_fastopen_blackhole_timeout_sec", + .data = &init_net.ipv4.sysctl_tcp_fastopen_blackhole_timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_tfo_blackhole_detect_timeout, + .extra1 = &zero, + }, #ifdef CONFIG_IP_ROUTE_MULTIPATH { .procname = "fib_multipath_use_neigh", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5091402720ab..3b34850d361f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -413,8 +413,10 @@ void tcp_init_sock(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); tp->out_of_order_queue = RB_ROOT; + sk->tcp_rtx_queue = RB_ROOT; tcp_init_xmit_timers(sk); INIT_LIST_HEAD(&tp->tsq_node); + INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); @@ -456,8 +458,22 @@ void tcp_init_sock(struct sock *sk) } EXPORT_SYMBOL(tcp_init_sock); -static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb) +void tcp_init_transfer(struct sock *sk, int bpf_op) { + struct inet_connection_sock *icsk = inet_csk(sk); + + tcp_mtup_init(sk); + icsk->icsk_af_ops->rebuild_header(sk); + tcp_init_metrics(sk); + tcp_call_bpf(sk, bpf_op); + tcp_init_congestion_control(sk); + tcp_init_buffer_space(sk); +} + +static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) +{ + struct sk_buff *skb = tcp_write_queue_tail(sk); + if (tsflags && skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); @@ -686,10 +702,9 @@ static void tcp_push(struct sock *sk, int flags, int mss_now, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - if (!tcp_send_head(sk)) - return; - skb = tcp_write_queue_tail(sk); + if (!skb) + return; if (!(flags & MSG_MORE) || forced_push(tp)) tcp_mark_push(tp, skb); @@ -869,6 +884,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, * available to the caller, no more, no less. */ skb->reserved_tailroom = skb->end - skb->tail - size; + INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); return skb; } __kfree_skb(skb); @@ -948,14 +964,14 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, int copy, i; bool can_coalesce; - if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0 || + if (!skb || (copy = size_goal - skb->len) <= 0 || !tcp_skb_can_collapse_to(skb)) { new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, - skb_queue_empty(&sk->sk_write_queue)); + tcp_rtx_and_write_queues_empty(sk)); if (!skb) goto wait_for_memory; @@ -1027,7 +1043,7 @@ wait_for_memory: out: if (copied) { - tcp_tx_timestamp(sk, sk->sk_tsflags, tcp_write_queue_tail(sk)); + tcp_tx_timestamp(sk, sk->sk_tsflags); if (!(flags & MSG_SENDPAGE_NOTLAST)) tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } @@ -1126,7 +1142,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, struct sockaddr *uaddr = msg->msg_name; int err, flags; - if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || + if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; @@ -1183,7 +1199,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) goto out_err; } - skb = tcp_send_head(sk) ? tcp_write_queue_tail(sk) : NULL; + skb = tcp_write_queue_tail(sk); uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb)); if (!uarg) { err = -ENOBUFS; @@ -1259,7 +1275,7 @@ restart: int max = size_goal; skb = tcp_write_queue_tail(sk); - if (tcp_send_head(sk)) { + if (skb) { if (skb->ip_summed == CHECKSUM_NONE) max = mss_now; copy = max - skb->len; @@ -1279,7 +1295,7 @@ new_segment: process_backlog = false; goto restart; } - first_skb = skb_queue_empty(&sk->sk_write_queue); + first_skb = tcp_rtx_and_write_queues_empty(sk); skb = sk_stream_alloc_skb(sk, select_size(sk, sg, first_skb), sk->sk_allocation, @@ -1404,7 +1420,7 @@ wait_for_memory: out: if (copied) { - tcp_tx_timestamp(sk, sockc.tsflags, tcp_write_queue_tail(sk)); + tcp_tx_timestamp(sk, sockc.tsflags); tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } out_nopush: @@ -1505,6 +1521,13 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) /* XXX -- need to support SO_PEEK_OFF */ + skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { + err = skb_copy_datagram_msg(skb, 0, msg, skb->len); + if (err) + return err; + copied += skb->len; + } + skb_queue_walk(&sk->sk_write_queue, skb) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) @@ -2304,6 +2327,37 @@ static inline bool tcp_need_reset(int state) TCPF_FIN_WAIT2 | TCPF_SYN_RECV); } +static void tcp_rtx_queue_purge(struct sock *sk) +{ + struct rb_node *p = rb_first(&sk->tcp_rtx_queue); + + while (p) { + struct sk_buff *skb = rb_to_skb(p); + + p = rb_next(p); + /* Since we are deleting whole queue, no need to + * list_del(&skb->tcp_tsorted_anchor) + */ + tcp_rtx_queue_unlink(skb, sk); + sk_wmem_free_skb(sk, skb); + } +} + +void tcp_write_queue_purge(struct sock *sk) +{ + struct sk_buff *skb; + + tcp_chrono_stop(sk, TCP_CHRONO_BUSY); + while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { + tcp_skb_tsorted_anchor_cleanup(skb); + sk_wmem_free_skb(sk, skb); + } + tcp_rtx_queue_purge(sk); + INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); + sk_mem_reclaim(sk); + tcp_clear_all_retrans_hints(tcp_sk(sk)); +} + int tcp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); @@ -2362,7 +2416,6 @@ int tcp_disconnect(struct sock *sk, int flags) * issue in __tcp_select_window() */ icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; - tcp_init_send_head(sk); memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); dst_release(sk->sk_rx_dst); @@ -2749,7 +2802,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_FASTOPEN: if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { - tcp_fastopen_init_key_once(true); + tcp_fastopen_init_key_once(net); fastopen_queue_tune(sk, val); } else { @@ -2759,7 +2812,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; - } else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { + } else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 66ac69f7bd19..06fbe102a425 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -389,7 +389,7 @@ static void tcp_cdg_release(struct sock *sk) kfree(ca->gradients); } -struct tcp_congestion_ops tcp_cdg __read_mostly = { +static struct tcp_congestion_ops tcp_cdg __read_mostly = { .cong_avoid = tcp_cdg_cong_avoid, .cwnd_event = tcp_cdg_cwnd_event, .pkts_acked = tcp_cdg_acked, diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index e3c33220c418..7ee4aadcdd71 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -9,15 +9,18 @@ #include <net/inetpeer.h> #include <net/tcp.h> -int sysctl_tcp_fastopen __read_mostly = TFO_CLIENT_ENABLE; - -struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; - -static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock); - -void tcp_fastopen_init_key_once(bool publish) +void tcp_fastopen_init_key_once(struct net *net) { - static u8 key[TCP_FASTOPEN_KEY_LENGTH]; + u8 key[TCP_FASTOPEN_KEY_LENGTH]; + struct tcp_fastopen_context *ctxt; + + rcu_read_lock(); + ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); + if (ctxt) { + rcu_read_unlock(); + return; + } + rcu_read_unlock(); /* tcp_fastopen_reset_cipher publishes the new context * atomically, so we allow this race happening here. @@ -25,8 +28,8 @@ void tcp_fastopen_init_key_once(bool publish) * All call sites of tcp_fastopen_cookie_gen also check * for a valid cookie, so this is an acceptable risk. */ - if (net_get_random_once(key, sizeof(key)) && publish) - tcp_fastopen_reset_cipher(key, sizeof(key)); + get_random_bytes(key, sizeof(key)); + tcp_fastopen_reset_cipher(net, key, sizeof(key)); } static void tcp_fastopen_ctx_free(struct rcu_head *head) @@ -37,7 +40,22 @@ static void tcp_fastopen_ctx_free(struct rcu_head *head) kfree(ctx); } -int tcp_fastopen_reset_cipher(void *key, unsigned int len) +void tcp_fastopen_ctx_destroy(struct net *net) +{ + struct tcp_fastopen_context *ctxt; + + spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); + + ctxt = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx, + lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); + rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, NULL); + spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); + + if (ctxt) + call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free); +} + +int tcp_fastopen_reset_cipher(struct net *net, void *key, unsigned int len) { int err; struct tcp_fastopen_context *ctx, *octx; @@ -61,26 +79,27 @@ error: kfree(ctx); } memcpy(ctx->key, key, len); - spin_lock(&tcp_fastopen_ctx_lock); + spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); - octx = rcu_dereference_protected(tcp_fastopen_ctx, - lockdep_is_held(&tcp_fastopen_ctx_lock)); - rcu_assign_pointer(tcp_fastopen_ctx, ctx); - spin_unlock(&tcp_fastopen_ctx_lock); + octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx, + lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); + rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx); + spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); if (octx) call_rcu(&octx->rcu, tcp_fastopen_ctx_free); return err; } -static bool __tcp_fastopen_cookie_gen(const void *path, +static bool __tcp_fastopen_cookie_gen(struct net *net, + const void *path, struct tcp_fastopen_cookie *foc) { struct tcp_fastopen_context *ctx; bool ok = false; rcu_read_lock(); - ctx = rcu_dereference(tcp_fastopen_ctx); + ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctx) { crypto_cipher_encrypt_one(ctx->tfm, foc->val, path); foc->len = TCP_FASTOPEN_COOKIE_SIZE; @@ -96,7 +115,8 @@ static bool __tcp_fastopen_cookie_gen(const void *path, * * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE. */ -static bool tcp_fastopen_cookie_gen(struct request_sock *req, +static bool tcp_fastopen_cookie_gen(struct net *net, + struct request_sock *req, struct sk_buff *syn, struct tcp_fastopen_cookie *foc) { @@ -104,7 +124,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, const struct iphdr *iph = ip_hdr(syn); __be32 path[4] = { iph->saddr, iph->daddr, 0, 0 }; - return __tcp_fastopen_cookie_gen(path, foc); + return __tcp_fastopen_cookie_gen(net, path, foc); } #if IS_ENABLED(CONFIG_IPV6) @@ -112,13 +132,13 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, const struct ipv6hdr *ip6h = ipv6_hdr(syn); struct tcp_fastopen_cookie tmp; - if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) { + if (__tcp_fastopen_cookie_gen(net, &ip6h->saddr, &tmp)) { struct in6_addr *buf = &tmp.addr; int i; for (i = 0; i < 4; i++) buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i]; - return __tcp_fastopen_cookie_gen(buf, foc); + return __tcp_fastopen_cookie_gen(net, buf, foc); } } #endif @@ -216,12 +236,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, refcount_set(&req->rsk_refcnt, 2); /* Now finish processing the fastopen child socket. */ - inet_csk(child)->icsk_af_ops->rebuild_header(child); - tcp_init_congestion_control(child); - tcp_mtup_init(child); - tcp_init_metrics(child); - tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); - tcp_init_buffer_space(child); + tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; @@ -279,25 +294,26 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc) { - struct tcp_fastopen_cookie valid_foc = { .len = -1 }; bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; + int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + struct tcp_fastopen_cookie valid_foc = { .len = -1 }; struct sock *child; if (foc->len == 0) /* Client requests a cookie */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD); - if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) && + if (!((tcp_fastopen & TFO_SERVER_ENABLE) && (syn_data || foc->len >= 0) && tcp_fastopen_queue_check(sk))) { foc->len = -1; return NULL; } - if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD)) + if (syn_data && (tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD)) goto fastopen; if (foc->len >= 0 && /* Client presents or requests a cookie */ - tcp_fastopen_cookie_gen(req, skb, &valid_foc) && + tcp_fastopen_cookie_gen(sock_net(sk), req, skb, &valid_foc) && foc->len == TCP_FASTOPEN_COOKIE_SIZE && foc->len == valid_foc.len && !memcmp(foc->val, valid_foc.val, foc->len)) { @@ -347,7 +363,7 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, return false; } - if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) { + if (sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) { cookie->len = -1; return true; } @@ -401,25 +417,16 @@ EXPORT_SYMBOL(tcp_fastopen_defer_connect); * TFO connection with data exchanges. */ -/* Default to 1hr */ -unsigned int sysctl_tcp_fastopen_blackhole_timeout __read_mostly = 60 * 60; -static atomic_t tfo_active_disable_times __read_mostly = ATOMIC_INIT(0); -static unsigned long tfo_active_disable_stamp __read_mostly; - /* Disable active TFO and record current jiffies and * tfo_active_disable_times */ void tcp_fastopen_active_disable(struct sock *sk) { - atomic_inc(&tfo_active_disable_times); - tfo_active_disable_stamp = jiffies; - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENBLACKHOLE); -} + struct net *net = sock_net(sk); -/* Reset tfo_active_disable_times to 0 */ -void tcp_fastopen_active_timeout_reset(void) -{ - atomic_set(&tfo_active_disable_times, 0); + atomic_inc(&net->ipv4.tfo_active_disable_times); + net->ipv4.tfo_active_disable_stamp = jiffies; + NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE); } /* Calculate timeout for tfo active disable @@ -428,17 +435,18 @@ void tcp_fastopen_active_timeout_reset(void) */ bool tcp_fastopen_active_should_disable(struct sock *sk) { - int tfo_da_times = atomic_read(&tfo_active_disable_times); - int multiplier; + unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout; + int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times); unsigned long timeout; + int multiplier; if (!tfo_da_times) return false; /* Limit timout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); - timeout = multiplier * sysctl_tcp_fastopen_blackhole_timeout * HZ; - if (time_before(jiffies, tfo_active_disable_stamp + timeout)) + timeout = multiplier * tfo_bh_timeout * HZ; + if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout)) return true; /* Mark check bit so we can check for successful active TFO @@ -457,27 +465,25 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) void tcp_fastopen_active_disable_ofo_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct rb_node *p; - struct sk_buff *skb; struct dst_entry *dst; + struct sk_buff *skb; if (!tp->syn_fastopen) return; if (!tp->data_segs_in) { - p = rb_first(&tp->out_of_order_queue); - if (p && !rb_next(p)) { - skb = rb_entry(p, struct sk_buff, rbnode); + skb = skb_rb_first(&tp->out_of_order_queue); + if (skb && !skb_rb_next(skb)) { if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_fastopen_active_disable(sk); return; } } } else if (tp->syn_fastopen_ch && - atomic_read(&tfo_active_disable_times)) { + atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) { dst = sk_dst_get(sk); if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK))) - tcp_fastopen_active_timeout_reset(); + atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0); dst_release(dst); } } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index db9bb46b5776..b2390bfdc68f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1142,6 +1142,7 @@ struct tcp_sacktag_state { u64 last_sackt; struct rate_sample *rate; int flag; + unsigned int mss_now; }; /* Check if skb is fully within the SACK block. In presence of GSO skbs, @@ -1191,7 +1192,8 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, if (pkt_len >= skb->len && !in_sack) return 0; - err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC); + err = tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + pkt_len, mss, GFP_ATOMIC); if (err < 0) return err; } @@ -1288,13 +1290,13 @@ static u8 tcp_sacktag_one(struct sock *sk, /* Shift newly-SACKed bytes from this skb to the immediately previous * already-SACKed sk_buff. Mark the newly-SACKed bytes as such. */ -static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, +static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev, + struct sk_buff *skb, struct tcp_sacktag_state *state, unsigned int pcount, int shifted, int mss, bool dup_sack) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *prev = tcp_write_queue_prev(sk, skb); u32 start_seq = TCP_SKB_CB(skb)->seq; /* start of newly-SACKed */ u32 end_seq = start_seq + shifted; /* end of newly-SACKed */ @@ -1363,8 +1365,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp)) TCP_SKB_CB(prev)->tx.delivered_mstamp = 0; - tcp_unlink_write_queue(skb, sk); - sk_wmem_free_skb(sk, skb); + tcp_rtx_queue_unlink_and_free(skb, sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKMERGED); @@ -1414,9 +1415,9 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, goto fallback; /* Can only happen with delayed DSACK + discard craziness */ - if (unlikely(skb == tcp_write_queue_head(sk))) + prev = skb_rb_prev(skb); + if (!prev) goto fallback; - prev = tcp_write_queue_prev(sk, skb); if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) goto fallback; @@ -1495,18 +1496,17 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, if (!skb_shift(prev, skb, len)) goto fallback; - if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack)) + if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack)) goto out; /* Hole filled allows collapsing with the next as well, this is very * useful when hole on every nth skb pattern happens */ - if (prev == tcp_write_queue_tail(sk)) + skb = skb_rb_next(prev); + if (!skb) goto out; - skb = tcp_write_queue_next(sk, prev); if (!skb_can_shift(skb) || - (skb == tcp_send_head(sk)) || ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) || (mss != tcp_skb_seglen(skb))) goto out; @@ -1514,7 +1514,8 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, len = skb->len; if (skb_shift(prev, skb, len)) { pcount += tcp_skb_pcount(skb); - tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0); + tcp_shifted_skb(sk, prev, skb, state, tcp_skb_pcount(skb), + len, mss, 0); } out: @@ -1538,13 +1539,10 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *tmp; - tcp_for_write_queue_from(skb, sk) { + skb_rbtree_walk_from(skb) { int in_sack = 0; bool dup_sack = dup_sack_in; - if (skb == tcp_send_head(sk)) - break; - /* queue is in-order => we can short-circuit the walk early */ if (!before(TCP_SKB_CB(skb)->seq, end_seq)) break; @@ -1593,6 +1591,8 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, tcp_skb_pcount(skb), skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) + list_del_init(&skb->tcp_tsorted_anchor); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) @@ -1604,23 +1604,44 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, return skb; } -/* Avoid all extra work that is being done by sacktag while walking in - * a normal way - */ +static struct sk_buff *tcp_sacktag_bsearch(struct sock *sk, + struct tcp_sacktag_state *state, + u32 seq) +{ + struct rb_node *parent, **p = &sk->tcp_rtx_queue.rb_node; + struct sk_buff *skb; + int unack_bytes; + + while (*p) { + parent = *p; + skb = rb_to_skb(parent); + if (before(seq, TCP_SKB_CB(skb)->seq)) { + p = &parent->rb_left; + continue; + } + if (!before(seq, TCP_SKB_CB(skb)->end_seq)) { + p = &parent->rb_right; + continue; + } + + state->fack_count = 0; + unack_bytes = TCP_SKB_CB(skb)->seq - tcp_sk(sk)->snd_una; + if (state->mss_now && unack_bytes > 0) + state->fack_count = unack_bytes / state->mss_now; + + return skb; + } + return NULL; +} + static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk, struct tcp_sacktag_state *state, u32 skip_to_seq) { - tcp_for_write_queue_from(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - - if (after(TCP_SKB_CB(skb)->end_seq, skip_to_seq)) - break; + if (skb && after(TCP_SKB_CB(skb)->seq, skip_to_seq)) + return skb; - state->fack_count += tcp_skb_pcount(skb); - } - return skb; + return tcp_sacktag_bsearch(sk, state, skip_to_seq); } static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, @@ -1742,8 +1763,9 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, } } - skb = tcp_write_queue_head(sk); + state->mss_now = tcp_current_mss(sk); state->fack_count = 0; + skb = NULL; i = 0; if (!tp->sacked_out) { @@ -1967,7 +1989,7 @@ void tcp_enter_loss(struct sock *sk) if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED); if (is_reneg) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING); @@ -1976,10 +1998,7 @@ void tcp_enter_loss(struct sock *sk) } tcp_clear_all_retrans_hints(tp); - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - + skb_rbtree_walk_from(skb) { mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || is_reneg); if (mark_lost) @@ -2205,20 +2224,18 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; WARN_ON(packets > tp->packets_out); - if (tp->lost_skb_hint) { - skb = tp->lost_skb_hint; - cnt = tp->lost_cnt_hint; + skb = tp->lost_skb_hint; + if (skb) { /* Head already handled? */ - if (mark_head && skb != tcp_write_queue_head(sk)) + if (mark_head && after(TCP_SKB_CB(skb)->seq, tp->snd_una)) return; + cnt = tp->lost_cnt_hint; } else { - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); cnt = 0; } - tcp_for_write_queue_from(skb, sk) { - if (skb == tcp_send_head(sk)) - break; + skb_rbtree_walk_from(skb) { /* TODO: do this better */ /* this is not the most efficient way to do this... */ tp->lost_skb_hint = skb; @@ -2242,7 +2259,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) /* If needed, chop off the prefix to mark as lost. */ lost = (packets - oldcnt) * mss; if (lost < skb->len && - tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0) + tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + lost, mss, GFP_ATOMIC) < 0) break; cnt = packets; } @@ -2326,7 +2344,7 @@ static bool tcp_any_retrans_done(const struct sock *sk) if (tp->retrans_out) return true; - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS)) return true; @@ -2367,9 +2385,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) if (unmark_loss) { struct sk_buff *skb; - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; + skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST; } tp->lost_out = 0; @@ -2614,9 +2630,7 @@ void tcp_simple_retransmit(struct sock *sk) unsigned int mss = tcp_current_mss(sk); u32 prior_lost = tp->lost_out; - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; + skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { if (tcp_skb_seglen(skb) > mss && !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { @@ -2710,7 +2724,7 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack, * is updated in tcp_ack()). Otherwise fall back to * the conventional recovery. */ - if (tcp_send_head(sk) && + if (!tcp_write_queue_empty(sk) && after(tcp_wnd_end(tp), tp->snd_nxt)) { *rexmit = REXMIT_NEW; return; @@ -2802,9 +2816,9 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); - if (WARN_ON(!tp->packets_out && tp->sacked_out)) + if (!tp->packets_out && tp->sacked_out) tp->sacked_out = 0; - if (WARN_ON(!tp->sacked_out && tp->fackets_out)) + if (!tp->sacked_out && tp->fackets_out) tp->fackets_out = 0; /* Now state machine starts. @@ -2871,6 +2885,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, (*ack_flag & FLAG_LOST_RETRANS))) return; /* Change state if cwnd is undone or retransmits are lost */ + /* fall through */ default: if (tcp_is_reno(tp)) { if (flag & FLAG_SND_UNA_ADVANCED) @@ -3054,8 +3069,11 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, shinfo = skb_shinfo(skb); if (!before(shinfo->tskey, prior_snd_una) && - before(shinfo->tskey, tcp_sk(sk)->snd_una)) - __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK); + before(shinfo->tskey, tcp_sk(sk)->snd_una)) { + tcp_skb_tsorted_save(skb) { + __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK); + } tcp_skb_tsorted_restore(skb); + } } /* Remove acknowledged frames from the retransmission queue. If our packet @@ -3071,11 +3089,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, struct tcp_sock *tp = tcp_sk(sk); u32 prior_sacked = tp->sacked_out; u32 reord = tp->packets_out; + struct sk_buff *skb, *next; bool fully_acked = true; long sack_rtt_us = -1L; long seq_rtt_us = -1L; long ca_rtt_us = -1L; - struct sk_buff *skb; u32 pkts_acked = 0; u32 last_in_flight = 0; bool rtt_update; @@ -3083,7 +3101,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, first_ackt = 0; - while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { + for (skb = skb_rb_first(&sk->tcp_rtx_queue); skb; skb = next) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); u8 sacked = scb->sacked; u32 acked_pcount; @@ -3101,8 +3119,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, break; fully_acked = false; } else { - /* Speedup tcp_unlink_write_queue() and next loop */ - prefetchw(skb->next); acked_pcount = tcp_skb_pcount(skb); } @@ -3154,12 +3170,12 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (!fully_acked) break; - tcp_unlink_write_queue(skb, sk); - sk_wmem_free_skb(sk, skb); + next = skb_rb_next(skb); if (unlikely(skb == tp->retransmit_skb_hint)) tp->retransmit_skb_hint = NULL; if (unlikely(skb == tp->lost_skb_hint)) tp->lost_skb_hint = NULL; + tcp_rtx_queue_unlink_and_free(skb, sk); } if (!skb) @@ -3251,12 +3267,14 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, static void tcp_ack_probe(struct sock *sk) { - const struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *head = tcp_send_head(sk); + const struct tcp_sock *tp = tcp_sk(sk); /* Was it a usable window open? */ - - if (!after(TCP_SKB_CB(tcp_send_head(sk))->end_seq, tcp_wnd_end(tp))) { + if (!head) + return; + if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) { icsk->icsk_backoff = 0; inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0); /* Socket must be waked up by subsequent tcp_data_snd_check(). @@ -3376,7 +3394,7 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 tp->pred_flags = 0; tcp_fast_path_check(sk); - if (tcp_send_head(sk)) + if (!tcp_write_queue_empty(sk)) tcp_slow_start_after_idle_check(sk); if (nwin > tp->max_window) { @@ -3561,8 +3579,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) sack_state.first_sackt = 0; sack_state.rate = &rs; - /* We very likely will need to access write queue head. */ - prefetchw(sk->sk_write_queue.next); + /* We very likely will need to access rtx queue. */ + prefetch(sk->tcp_rtx_queue.rb_node); /* If the ack is older than previous acks * then we can probably ignore it. @@ -3676,8 +3694,7 @@ no_queue: * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. */ - if (tcp_send_head(sk)) - tcp_ack_probe(sk); + tcp_ack_probe(sk); if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); @@ -4330,7 +4347,7 @@ static void tcp_ofo_queue(struct sock *sk) p = rb_first(&tp->out_of_order_queue); while (p) { - skb = rb_entry(p, struct sk_buff, rbnode); + skb = rb_to_skb(p); if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; @@ -4394,7 +4411,7 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - struct rb_node **p, *q, *parent; + struct rb_node **p, *parent; struct sk_buff *skb1; u32 seq, end_seq; bool fragstolen; @@ -4453,7 +4470,7 @@ coalesce_done: parent = NULL; while (*p) { parent = *p; - skb1 = rb_entry(parent, struct sk_buff, rbnode); + skb1 = rb_to_skb(parent); if (before(seq, TCP_SKB_CB(skb1)->seq)) { p = &parent->rb_left; continue; @@ -4498,9 +4515,7 @@ insert: merge_right: /* Remove other segments covered by skb. */ - while ((q = rb_next(&skb->rbnode)) != NULL) { - skb1 = rb_entry(q, struct sk_buff, rbnode); - + while ((skb1 = skb_rb_next(skb)) != NULL) { if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) break; if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) { @@ -4515,7 +4530,7 @@ merge_right: tcp_drop(sk, skb1); } /* If there is no skb after us, we are the last_skb ! */ - if (!q) + if (!skb1) tp->ooo_last_skb = skb; add_sack: @@ -4701,7 +4716,7 @@ static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *li if (list) return !skb_queue_is_last(list, skb) ? skb->next : NULL; - return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode); + return skb_rb_next(skb); } static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, @@ -4722,7 +4737,7 @@ static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, } /* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */ -static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) +void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -4730,7 +4745,7 @@ static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) while (*p) { parent = *p; - skb1 = rb_entry(parent, struct sk_buff, rbnode); + skb1 = rb_to_skb(parent); if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq)) p = &parent->rb_left; else @@ -4849,26 +4864,19 @@ static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb, *head; - struct rb_node *p; u32 start, end; - p = rb_first(&tp->out_of_order_queue); - skb = rb_entry_safe(p, struct sk_buff, rbnode); + skb = skb_rb_first(&tp->out_of_order_queue); new_range: if (!skb) { - p = rb_last(&tp->out_of_order_queue); - /* Note: This is possible p is NULL here. We do not - * use rb_entry_safe(), as ooo_last_skb is valid only - * if rbtree is not empty. - */ - tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode); + tp->ooo_last_skb = skb_rb_last(&tp->out_of_order_queue); return; } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; for (head = skb;;) { - skb = tcp_skb_next(skb, NULL); + skb = skb_rb_next(skb); /* Range is terminated when we see a gap or when * we are at the queue end. @@ -4911,14 +4919,14 @@ static bool tcp_prune_ofo_queue(struct sock *sk) do { prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); - tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode)); + tcp_drop(sk, rb_to_skb(node)); sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !tcp_under_memory_pressure(sk)) break; node = prev; } while (node); - tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode); + tp->ooo_last_skb = rb_to_skb(prev); /* Reset SACK state. A conforming SACK implementation will * do the same at a timeout based retransmit. When a connection @@ -5513,20 +5521,13 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) security_inet_conn_established(sk, skb); } - /* Make sure socket is routed, for correct metrics. */ - icsk->icsk_af_ops->rebuild_header(sk); - - tcp_init_metrics(sk); - tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); - tcp_init_congestion_control(sk); + tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); /* Prevent spurious tcp_cwnd_restart() on first data * packet. */ tp->lsndtime = tcp_jiffies32; - tcp_init_buffer_space(sk); - if (sock_flag(sk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp)); @@ -5540,7 +5541,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, struct tcp_fastopen_cookie *cookie) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL; + struct sk_buff *data = tp->syn_data ? tcp_rtx_queue_head(sk) : NULL; u16 mss = tp->rx_opt.mss_clamp, try_exp = 0; bool syn_drop = false; @@ -5575,9 +5576,8 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp); if (data) { /* Retransmit unacked data in SYN */ - tcp_for_write_queue_from(data, sk) { - if (data == tcp_send_head(sk) || - __tcp_retransmit_skb(sk, data, 1)) + skb_rbtree_walk_from(data) { + if (__tcp_retransmit_skb(sk, data, 1)) break; } tcp_rearm_rto(sk); @@ -5693,7 +5693,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, if (tcp_is_sack(tp) && sysctl_tcp_fack) tcp_enable_fack(tp); - tcp_mtup_init(sk); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); @@ -5919,15 +5918,18 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (req) { inet_csk(sk)->icsk_retransmits = 0; reqsk_fastopen_remove(sk, req, false); + /* Re-arm the timer because data may have been sent out. + * This is similar to the regular data transmission case + * when new data has just been ack'ed. + * + * (TFO) - we could try to be more aggressive and + * retransmitting any data sooner based on when they + * are sent out. + */ + tcp_rearm_rto(sk); } else { - /* Make sure socket is routed, for correct metrics. */ - icsk->icsk_af_ops->rebuild_header(sk); - tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); - tcp_init_congestion_control(sk); - - tcp_mtup_init(sk); + tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tp->copied_seq = tp->rcv_nxt; - tcp_init_buffer_space(sk); } smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); @@ -5947,19 +5949,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; - if (req) { - /* Re-arm the timer because data may have been sent out. - * This is similar to the regular data transmission case - * when new data has just been ack'ed. - * - * (TFO) - we could try to be more aggressive and - * retransmitting any data sooner based on when they - * are sent out. - */ - tcp_rearm_rto(sk); - } else - tcp_init_metrics(sk); - if (!inet_csk(sk)->icsk_ca_ops->cong_control) tcp_update_pacing_rate(sk); @@ -6056,6 +6045,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_LAST_ACK: if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; + /* fall through */ case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: /* RFC 793 says to queue data in these states, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d9416b5162bc..ecee4ddb24c5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -480,7 +480,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) TCP_TIMEOUT_INIT; icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); BUG_ON(!skb); tcp_mstamp_refresh(tp); @@ -1503,23 +1503,23 @@ csum_err: } EXPORT_SYMBOL(tcp_v4_do_rcv); -void tcp_v4_early_demux(struct sk_buff *skb) +int tcp_v4_early_demux(struct sk_buff *skb) { const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) - return; + return 0; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) - return; + return 0; iph = ip_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) - return; + return 0; sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, iph->saddr, th->source, @@ -1538,6 +1538,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) skb_dst_set_noref(skb, dst); } } + return 0; } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) @@ -1778,8 +1779,9 @@ do_time_wait: refcounted = false; goto process; } - /* Fall through to ACK */ } + /* to ACK */ + /* fall through */ case TCP_TW_ACK: tcp_v4_timewait_ack(sk, skb); break; @@ -2472,6 +2474,11 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_window_scaling = 1; net->ipv4.sysctl_tcp_timestamps = 1; + net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; + spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); + net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60; + atomic_set(&net->ipv4.tfo_active_disable_times, 0); + return 0; fail: tcp_sk_exit(net); @@ -2481,7 +2488,12 @@ fail: static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { + struct net *net; + inet_twsk_purge(&tcp_hashinfo, AF_INET); + + list_for_each_entry(net, net_exit_list, exit_list) + tcp_fastopen_ctx_destroy(net); } static struct pernet_operations __net_initdata tcp_sk_ops = { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 188a6f31356d..2341b9f857b6 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -446,6 +446,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; INIT_LIST_HEAD(&newtp->tsq_node); + INIT_LIST_HEAD(&newtp->tsorted_sent_queue); tcp_init_wl(newtp, treq->rcv_isn); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0bc9e46a5369..53dc1267c85e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -42,6 +42,8 @@ #include <linux/gfp.h> #include <linux/module.h> +#include <trace/events/tcp.h> + /* People can turn this off for buggy TCP's found in printers etc. */ int sysctl_tcp_retrans_collapse __read_mostly = 1; @@ -66,15 +68,17 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ -static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) +static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; - tcp_advance_send_head(sk, skb); tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; + __skb_unlink(skb, &sk->sk_write_queue); + tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); + tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); @@ -971,6 +975,12 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) HRTIMER_MODE_ABS_PINNED); } +static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) +{ + skb->skb_mstamp = tp->tcp_mstamp; + list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); +} + /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. @@ -1003,10 +1013,14 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq - tp->snd_una; oskb = skb; - if (unlikely(skb_cloned(skb))) - skb = pskb_copy(skb, gfp_mask); - else - skb = skb_clone(skb, gfp_mask); + + tcp_skb_tsorted_save(oskb) { + if (unlikely(skb_cloned(oskb))) + skb = pskb_copy(oskb, gfp_mask); + else + skb = skb_clone(oskb, gfp_mask); + } tcp_skb_tsorted_restore(oskb); + if (unlikely(!skb)) return -ENOBUFS; } @@ -1127,7 +1141,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, err = net_xmit_eval(err); } if (!err && oskb) { - oskb->skb_mstamp = tp->tcp_mstamp; + tcp_update_skb_after_send(tp, oskb); tcp_rate_skb_sent(sk, oskb); } return err; @@ -1239,12 +1253,25 @@ static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2) TCP_SKB_CB(skb)->eor = 0; } +/* Insert buff after skb on the write or rtx queue of sk. */ +static void tcp_insert_write_queue_after(struct sk_buff *skb, + struct sk_buff *buff, + struct sock *sk, + enum tcp_queue tcp_queue) +{ + if (tcp_queue == TCP_FRAG_IN_WRITE_QUEUE) + __skb_queue_after(&sk->sk_write_queue, skb, buff); + else + tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); +} + /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. * Remember, these are still headerless SKBs at this point. */ -int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, +int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, + struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); @@ -1327,7 +1354,8 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, /* Link BUFF into the send queue. */ __skb_header_release(buff); - tcp_insert_write_queue_after(skb, buff, sk); + tcp_insert_write_queue_after(skb, buff, sk, tcp_queue); + list_add(&buff->tcp_tsorted_anchor, &skb->tcp_tsorted_anchor); return 0; } @@ -1614,10 +1642,10 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) * is caused by insufficient sender buffer: * 1) just sent some data (see tcp_write_xmit) * 2) not cwnd limited (this else condition) - * 3) no more data to send (null tcp_send_head ) + * 3) no more data to send (tcp_write_queue_empty()) * 4) application is hitting buffer limit (SOCK_NOSPACE) */ - if (!tcp_send_head(sk) && sk->sk_socket && + if (tcp_write_queue_empty(sk) && sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags) && (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) tcp_chrono_start(sk, TCP_CHRONO_SNDBUF_LIMITED); @@ -1813,7 +1841,8 @@ static bool tcp_snd_wnd_test(const struct tcp_sock *tp, * know that all the data is in scatter-gather pages, and that the * packet has never been sent out before (and thus is not cloned). */ -static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, +static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue, + struct sk_buff *skb, unsigned int len, unsigned int mss_now, gfp_t gfp) { struct sk_buff *buff; @@ -1822,7 +1851,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, /* All of a TSO frame must be composed of paged data. */ if (skb->len != skb->data_len) - return tcp_fragment(sk, skb, len, mss_now, gfp); + return tcp_fragment(sk, tcp_queue, skb, len, mss_now, gfp); buff = sk_stream_alloc_skb(sk, 0, gfp, true); if (unlikely(!buff)) @@ -1858,7 +1887,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, /* Link BUFF into the send queue. */ __skb_header_release(buff); - tcp_insert_write_queue_after(skb, buff, sk); + tcp_insert_write_queue_after(skb, buff, sk, tcp_queue); return 0; } @@ -1928,8 +1957,10 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, goto send_now; } - head = tcp_write_queue_head(sk); - + /* TODO : use tsorted_sent_queue ? */ + head = tcp_rtx_queue_head(sk); + if (!head) + goto send_now; age = tcp_stamp_us_delta(tp->tcp_mstamp, head->skb_mstamp); /* If next ACK is likely to come too late (half srtt), do not defer */ if (age < (tp->srtt_us >> 4)) @@ -2147,13 +2178,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit <<= factor; if (refcount_read(&sk->sk_wmem_alloc) > limit) { - /* Always send the 1st or 2nd skb in write queue. + /* Always send skb if rtx queue is empty. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ - if (skb == sk->sk_write_queue.next || - skb->prev == sk->sk_write_queue.next) + if (tcp_rtx_queue_empty(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); @@ -2204,7 +2234,7 @@ void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) * it's the "most interesting" or current chrono we are * tracking and starts busy chrono if we have pending data. */ - if (tcp_write_queue_empty(sk)) + if (tcp_rtx_and_write_queues_empty(sk)) tcp_chrono_set(tp, TCP_CHRONO_UNSPEC); else if (type == tp->chrono_type) tcp_chrono_set(tp, TCP_CHRONO_BUSY); @@ -2260,7 +2290,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp" is used as a start point for the retransmit timer */ - skb->skb_mstamp = tp->tcp_mstamp; + tcp_update_skb_after_send(tp, skb); goto repair; /* Skip network transmission */ } @@ -2299,7 +2329,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, nonagle); if (skb->len > limit && - unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) + unlikely(tso_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, + skb, limit, mss_now, gfp))) break; if (test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) @@ -2339,7 +2370,7 @@ repair: tcp_cwnd_validate(sk, is_cwnd_limited); return false; } - return !tp->packets_out && tcp_send_head(sk); + return !tp->packets_out && !tcp_write_queue_empty(sk); } bool tcp_schedule_loss_probe(struct sock *sk) @@ -2363,7 +2394,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) return false; if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) && - tcp_send_head(sk)) + !tcp_write_queue_empty(sk)) return false; /* Probe timeout is 2*rtt. Add minimum RTO to account @@ -2416,18 +2447,14 @@ void tcp_send_loss_probe(struct sock *sk) int mss = tcp_current_mss(sk); skb = tcp_send_head(sk); - if (skb) { - if (tcp_snd_wnd_test(tp, skb, mss)) { - pcount = tp->packets_out; - tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); - if (tp->packets_out > pcount) - goto probe_sent; - goto rearm_timer; - } - skb = tcp_write_queue_prev(sk, skb); - } else { - skb = tcp_write_queue_tail(sk); + if (skb && tcp_snd_wnd_test(tp, skb, mss)) { + pcount = tp->packets_out; + tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); + if (tp->packets_out > pcount) + goto probe_sent; + goto rearm_timer; } + skb = skb_rb_last(&sk->tcp_rtx_queue); /* At most one outstanding TLP retransmission. */ if (tp->tlp_high_seq) @@ -2445,10 +2472,11 @@ void tcp_send_loss_probe(struct sock *sk) goto rearm_timer; if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) { - if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss, + if (unlikely(tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + (pcount - 1) * mss, mss, GFP_ATOMIC))) goto rearm_timer; - skb = tcp_write_queue_next(sk, skb); + skb = skb_rb_next(skb); } if (WARN_ON(!skb || !tcp_skb_pcount(skb))) @@ -2648,7 +2676,7 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb, static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *next_skb = tcp_write_queue_next(sk, skb); + struct sk_buff *next_skb = skb_rb_next(skb); int skb_size, next_skb_size; skb_size = skb->len; @@ -2665,8 +2693,6 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) } tcp_highest_sack_combine(sk, next_skb, skb); - tcp_unlink_write_queue(next_skb, sk); - if (next_skb->ip_summed == CHECKSUM_PARTIAL) skb->ip_summed = CHECKSUM_PARTIAL; @@ -2694,7 +2720,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) tcp_skb_collapse_tstamp(skb, next_skb); - sk_wmem_free_skb(sk, next_skb); + tcp_rtx_queue_unlink_and_free(next_skb, sk); return true; } @@ -2705,8 +2731,6 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) return false; if (skb_cloned(skb)) return false; - if (skb == tcp_send_head(sk)) - return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; @@ -2729,7 +2753,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; - tcp_for_write_queue_from_safe(skb, tmp, sk) { + skb_rbtree_walk_from_safe(skb, tmp) { if (!tcp_can_collapse(sk, skb)) break; @@ -2804,7 +2828,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) len = cur_mss * segs; if (skb->len > len) { - if (tcp_fragment(sk, skb, len, cur_mss, GFP_ATOMIC)) + if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len, + cur_mss, GFP_ATOMIC)) return -ENOMEM; /* We'll try again later. */ } else { if (skb_unclone(skb, GFP_ATOMIC)) @@ -2838,17 +2863,21 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb; - nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); - err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : - -ENOBUFS; + tcp_skb_tsorted_save(skb) { + nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); + err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : + -ENOBUFS; + } tcp_skb_tsorted_restore(skb); + if (!err) - skb->skb_mstamp = tp->tcp_mstamp; + tcp_update_skb_after_send(tp, skb); } else { err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } if (likely(!err)) { TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + trace_tcp_retransmit_skb(sk, skb); } else if (err != -EBUSY) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); } @@ -2892,29 +2921,21 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) void tcp_xmit_retransmit_queue(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *skb, *rtx_head, *hole = NULL; struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - struct sk_buff *hole = NULL; u32 max_segs; int mib_idx; if (!tp->packets_out) return; - if (tp->retransmit_skb_hint) { - skb = tp->retransmit_skb_hint; - } else { - skb = tcp_write_queue_head(sk); - } - + rtx_head = tcp_rtx_queue_head(sk); + skb = tp->retransmit_skb_hint ?: rtx_head; max_segs = tcp_tso_segs(sk, tcp_current_mss(sk)); - tcp_for_write_queue_from(skb, sk) { + skb_rbtree_walk_from(skb) { __u8 sacked; int segs; - if (skb == tcp_send_head(sk)) - break; - if (tcp_pacing_check(sk)) break; @@ -2959,7 +2980,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); - if (skb == tcp_write_queue_head(sk) && + if (skb == rtx_head && icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT) inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, @@ -3001,12 +3022,15 @@ void tcp_send_fin(struct sock *sk) * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ - if (tskb && (tcp_send_head(sk) || tcp_under_memory_pressure(sk))) { + if (!tskb && tcp_under_memory_pressure(sk)) + tskb = skb_rb_last(&sk->tcp_rtx_queue); + + if (tskb) { coalesce: TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; - if (!tcp_send_head(sk)) { + if (tcp_write_queue_empty(sk)) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have @@ -3023,6 +3047,7 @@ coalesce: goto coalesce; return; } + INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); skb_reserve(skb, MAX_TCP_HEADER); sk_forced_mem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ @@ -3071,20 +3096,24 @@ int tcp_send_synack(struct sock *sk) { struct sk_buff *skb; - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { - pr_debug("%s: wrong queue state\n", __func__); + pr_err("%s: wrong queue state\n", __func__); return -EFAULT; } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { if (skb_cloned(skb)) { - struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC); + struct sk_buff *nskb; + + tcp_skb_tsorted_save(skb) { + nskb = skb_copy(skb, GFP_ATOMIC); + } tcp_skb_tsorted_restore(skb); if (!nskb) return -ENOMEM; - tcp_unlink_write_queue(skb, sk); + INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); + tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); - __tcp_add_write_queue_head(sk, nskb); - sk_wmem_free_skb(sk, skb); + tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); sk->sk_wmem_queued += nskb->truesize; sk_mem_charge(sk, nskb->truesize); skb = nskb; @@ -3307,7 +3336,6 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) tcb->end_seq += skb->len; __skb_header_release(skb); - __tcp_add_write_queue_tail(sk, skb); sk->sk_wmem_queued += skb->truesize; sk_mem_charge(sk, skb->truesize); tp->write_seq = tcb->end_seq; @@ -3385,12 +3413,13 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH; if (!err) { tp->syn_data = (fo->copied > 0); + tcp_rbtree_insert(&sk->tcp_rtx_queue, syn_data); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); goto done; } - /* data was not sent, this is our new send_head */ - sk->sk_send_head = syn_data; + /* data was not sent, put it in write_queue */ + __skb_queue_tail(&sk->sk_write_queue, syn_data); tp->packets_out -= tcp_skb_pcount(syn_data); fallback: @@ -3433,6 +3462,7 @@ int tcp_connect(struct sock *sk) tp->retrans_stamp = tcp_time_stamp(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); + tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); /* Send off SYN; include data in Fast Open. */ err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) : @@ -3627,7 +3657,8 @@ int tcp_write_wakeup(struct sock *sk, int mib) skb->len > mss) { seg_size = min(seg_size, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; - if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC)) + if (tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, + skb, seg_size, mss, GFP_ATOMIC)) return -1; } else if (!tcp_skb_pcount(skb)) tcp_set_skb_tso_segs(skb, mss); @@ -3657,7 +3688,7 @@ void tcp_send_probe0(struct sock *sk) err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE); - if (tp->packets_out || !tcp_send_head(sk)) { + if (tp->packets_out || tcp_write_queue_empty(sk)) { /* Cancel probe timer, if it is not required. */ icsk->icsk_probes_out = 0; icsk->icsk_backoff = 0; diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 449cd914d58e..cda6074a429a 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -45,7 +45,7 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; + struct sk_buff *skb, *n; u32 reo_wnd; *reo_timeout = 0; @@ -58,45 +58,31 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) if ((tp->rack.reord || !tp->lost_out) && tcp_min_rtt(tp) != ~0U) reo_wnd = max(tcp_min_rtt(tp) >> 2, reo_wnd); - tcp_for_write_queue(skb, sk) { + list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue, + tcp_tsorted_anchor) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + s32 remaining; - if (skb == tcp_send_head(sk)) - break; - - /* Skip ones already (s)acked */ - if (!after(scb->end_seq, tp->snd_una) || - scb->sacked & TCPCB_SACKED_ACKED) + /* Skip ones marked lost but not yet retransmitted */ + if ((scb->sacked & TCPCB_LOST) && + !(scb->sacked & TCPCB_SACKED_RETRANS)) continue; - if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp, - tp->rack.end_seq, scb->end_seq)) { - /* Step 3 in draft-cheng-tcpm-rack-00.txt: - * A packet is lost if its elapsed time is beyond - * the recent RTT plus the reordering window. - */ - u32 elapsed = tcp_stamp_us_delta(tp->tcp_mstamp, - skb->skb_mstamp); - s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed; - - if (remaining < 0) { - tcp_rack_mark_skb_lost(sk, skb); - continue; - } - - /* Skip ones marked lost but not yet retransmitted */ - if ((scb->sacked & TCPCB_LOST) && - !(scb->sacked & TCPCB_SACKED_RETRANS)) - continue; + if (!tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp, + tp->rack.end_seq, scb->end_seq)) + break; + /* A packet is lost if it has not been s/acked beyond + * the recent RTT plus the reordering window. + */ + remaining = tp->rack.rtt_us + reo_wnd - + tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp); + if (remaining < 0) { + tcp_rack_mark_skb_lost(sk, skb); + list_del_init(&skb->tcp_tsorted_anchor); + } else { /* Record maximum wait time (+1 to avoid 0) */ *reo_timeout = max_t(u32, *reo_timeout, 1 + remaining); - - } else if (!(scb->sacked & TCPCB_RETRANS)) { - /* Original data are sent sequentially so stop early - * b/c the rest are all sent after rack_sent - */ - break; } } } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 655dd8d7f064..804a8d34ce86 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -156,8 +156,13 @@ static bool retransmits_timed_out(struct sock *sk, return false; start_ts = tcp_sk(sk)->retrans_stamp; - if (unlikely(!start_ts)) - start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk)); + if (unlikely(!start_ts)) { + struct sk_buff *head = tcp_rtx_queue_head(sk); + + if (!head) + return false; + start_ts = tcp_skb_timestamp(head); + } if (likely(timeout == 0)) { linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); @@ -283,15 +288,17 @@ out: * * Returns: Nothing (void) */ -static void tcp_delack_timer(unsigned long data) +static void tcp_delack_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_delack_timer); + struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { tcp_delack_timer_handler(sk); } else { - inet_csk(sk)->icsk_ack.blocked = 1; + icsk->icsk_ack.blocked = 1; __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); /* deleguate our work to tcp_release_cb() */ if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) @@ -304,11 +311,12 @@ static void tcp_delack_timer(unsigned long data) static void tcp_probe_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *skb = tcp_send_head(sk); struct tcp_sock *tp = tcp_sk(sk); int max_probes; u32 start_ts; - if (tp->packets_out || !tcp_send_head(sk)) { + if (tp->packets_out || !skb) { icsk->icsk_probes_out = 0; return; } @@ -321,9 +329,9 @@ static void tcp_probe_timer(struct sock *sk) * corresponding system limit. We also implement similar policy when * we use RTO to probe window in tcp_retransmit_timer(). */ - start_ts = tcp_skb_timestamp(tcp_send_head(sk)); + start_ts = tcp_skb_timestamp(skb); if (!start_ts) - tcp_send_head(sk)->skb_mstamp = tp->tcp_mstamp; + skb->skb_mstamp = tp->tcp_mstamp; else if (icsk->icsk_user_timeout && (s32)(tcp_time_stamp(tp) - start_ts) > jiffies_to_msecs(icsk->icsk_user_timeout)) @@ -408,7 +416,7 @@ void tcp_retransmit_timer(struct sock *sk) if (!tp->packets_out) goto out; - WARN_ON(tcp_write_queue_empty(sk)); + WARN_ON(tcp_rtx_queue_empty(sk)); tp->tlp_high_seq = 0; @@ -441,7 +449,7 @@ void tcp_retransmit_timer(struct sock *sk) goto out; } tcp_enter_loss(sk); - tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1); + tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1); __sk_dst_reset(sk); goto out_reset_timer; } @@ -473,7 +481,7 @@ void tcp_retransmit_timer(struct sock *sk) tcp_enter_loss(sk); - if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1) > 0) { + if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) { /* Retransmission failed because of local congestion, * do not backoff. */ @@ -570,9 +578,11 @@ out: sk_mem_reclaim(sk); } -static void tcp_write_timer(unsigned long data) +static void tcp_write_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_retransmit_timer); + struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { @@ -607,9 +617,9 @@ void tcp_set_keepalive(struct sock *sk, int val) EXPORT_SYMBOL_GPL(tcp_set_keepalive); -static void tcp_keepalive_timer (unsigned long data) +static void tcp_keepalive_timer (struct timer_list *t) { - struct sock *sk = (struct sock *) data; + struct sock *sk = from_timer(sk, t, sk_timer); struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 elapsed; @@ -647,7 +657,7 @@ static void tcp_keepalive_timer (unsigned long data) elapsed = keepalive_time_when(tp); /* It is alive without keepalive 8) */ - if (tp->packets_out || tcp_send_head(sk)) + if (tp->packets_out || !tcp_write_queue_empty(sk)) goto resched; elapsed = keepalive_time_elapsed(tp); diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 218cfcc77650..ee113ff15fd0 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -158,7 +158,7 @@ EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event); static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp) { - return min(tp->snd_ssthresh, tp->snd_cwnd-1); + return min(tp->snd_ssthresh, tp->snd_cwnd); } static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 784ced0b9150..7c9a6e4a7253 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2220,9 +2220,10 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, return NULL; } -void udp_v4_early_demux(struct sk_buff *skb) +int udp_v4_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + struct in_device *in_dev = NULL; const struct iphdr *iph; const struct udphdr *uh; struct sock *sk = NULL; @@ -2233,25 +2234,21 @@ void udp_v4_early_demux(struct sk_buff *skb) /* validate the packet */ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) - return; + return 0; iph = ip_hdr(skb); uh = udp_hdr(skb); - if (skb->pkt_type == PACKET_BROADCAST || - skb->pkt_type == PACKET_MULTICAST) { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); + if (skb->pkt_type == PACKET_MULTICAST) { + in_dev = __in_dev_get_rcu(skb->dev); if (!in_dev) - return; + return 0; - /* we are supposed to accept bcast packets */ - if (skb->pkt_type == PACKET_MULTICAST) { - ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, - iph->protocol); - if (!ours) - return; - } + ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, + iph->protocol); + if (!ours) + return 0; sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, @@ -2262,7 +2259,7 @@ void udp_v4_early_demux(struct sk_buff *skb) } if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) - return; + return 0; skb->sk = sk; skb->destructor = sock_efree; @@ -2271,12 +2268,23 @@ void udp_v4_early_demux(struct sk_buff *skb) if (dst) dst = dst_check(dst, 0); if (dst) { + u32 itag = 0; + /* set noref for now. * any place which wants to hold dst has to call * dst_hold_safe() */ skb_dst_set_noref(skb, dst); + + /* for unconnected multicast sockets we need to validate + * the source on each packet + */ + if (!inet_sk(sk)->inet_daddr && in_dev) + return ip_mc_validate_source(skb, iph->daddr, + iph->saddr, iph->tos, + skb->dev, in_dev, &itag); } + return 0; } int udp_rcv(struct sk_buff *skb) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 97658bfc1b58..e360d55be555 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -120,7 +120,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ - if (gso_partial) { + if (gso_partial && skb_is_gso(skb)) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); |